Typedefs | Enumerations | Functions

HTMLparser.h File Reference

HTML parser, doesn't support HTML5. More...

Typedefs

typedef xmlParserCtxt htmlParserCtxt

Same as xmlParserCtxt.

typedef xmlSAXHandler htmlSAXHandler

Same as xmlSAXHandler.

typedef xmlParserInput htmlParserInput

Same as xmlParserInput.

Enumerations

enum htmlParserOption

This is the set of HTML parser options that can be passed to htmlReadDoc, htmlCtxtSetOptions and other functions. More...

enum htmlStatus

deprecated content model

Functions

void htmlInitAutoClose (void)

const htmlElemDesc * htmlTagLookup (const xmlChar *tag)

Lookup the HTML tag in the ElementTable.

const htmlEntityDesc * htmlEntityLookup (const xmlChar *name)

Lookup the given entity in EntitiesTable.

const htmlEntityDesc * htmlEntityValueLookup (unsigned int value)

Lookup the given entity in EntitiesTable.

int htmlIsAutoClosed (xmlDoc *doc, xmlNode *elem)

The HTML DTD allows a tag to implicitly close other tags.

int htmlAutoCloseTag (xmlDoc *doc, const xmlChar *name, xmlNode *elem)

The HTML DTD allows a tag to implicitly close other tags.

const htmlEntityDesc * htmlParseEntityRef (htmlParserCtxt *ctxt, const xmlChar **str)

int htmlParseCharRef (htmlParserCtxt *ctxt)

void htmlParseElement (htmlParserCtxt *ctxt)

This is kept for compatibility with previous code versions.

htmlParserCtxt * htmlNewParserCtxt (void)

Allocate and initialize a new HTML parser context.

htmlParserCtxt * htmlNewSAXParserCtxt (const htmlSAXHandler *sax, void *userData)

Allocate and initialize a new HTML SAX parser context.

htmlParserCtxt * htmlCreateMemoryParserCtxt (const char *buffer, int size)

Create a parser context for an HTML in-memory document.

int htmlParseDocument (htmlParserCtxt *ctxt)

Parse an HTML document and invoke the SAX handlers.

xmlDoc * htmlSAXParseDoc (const xmlChar *cur, const char *encoding, htmlSAXHandler *sax, void *userData)

Parse an HTML in-memory document.

xmlDoc * htmlParseDoc (const xmlChar *cur, const char *encoding)

Parse an HTML in-memory document and build a tree.

htmlParserCtxt * htmlCreateFileParserCtxt (const char *filename, const char *encoding)

Create a parser context to read from a file.

xmlDoc * htmlSAXParseFile (const char *filename, const char *encoding, htmlSAXHandler *sax, void *userData)

parse an HTML file and build a tree.

xmlDoc * htmlParseFile (const char *filename, const char *encoding)

Parse an HTML file and build a tree.

int htmlUTF8ToHtml (unsigned char *out, int *outlen, const unsigned char *in, int *inlen)

Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.

int htmlEncodeEntities (unsigned char *out, int *outlen, const unsigned char *in, int *inlen, int quoteChar)

Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.

int htmlIsScriptAttribute (const xmlChar *name)

Check if an attribute is of content type Script.

int htmlHandleOmittedElem (int val)

Set and return the previous value for handling HTML omitted tags.

htmlParserCtxt * htmlCreatePushParserCtxt (htmlSAXHandler *sax, void *user_data, const char *chunk, int size, const char *filename, xmlCharEncoding enc)

Create a parser context for using the HTML parser in push mode.

int htmlParseChunk (htmlParserCtxt *ctxt, const char *chunk, int size, int terminate)

Parse a chunk of memory in push parser mode.

void htmlFreeParserCtxt (htmlParserCtxt *ctxt)

Free all the memory used by a parser context.

void htmlCtxtReset (htmlParserCtxt *ctxt)

Reset a parser context.

int htmlCtxtSetOptions (htmlParserCtxt *ctxt, int options)

Applies the options to the parser context.

int htmlCtxtUseOptions (htmlParserCtxt *ctxt, int options)

Applies the options to the parser context.

xmlDoc * htmlReadDoc (const xmlChar *cur, const char *URL, const char *encoding, int options)

Convenience function to parse an HTML document from a zero-terminated string.

xmlDoc * htmlReadFile (const char *URL, const char *encoding, int options)

Convenience function to parse an HTML file from the filesystem, the network or a global user-defined resource loader.

xmlDoc * htmlReadMemory (const char *buffer, int size, const char *URL, const char *encoding, int options)

Convenience function to parse an HTML document from memory.

xmlDoc * htmlReadFd (int fd, const char *URL, const char *encoding, int options)

Convenience function to parse an HTML document from a file descriptor.

xmlDoc * htmlReadIO (xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void *ioctx, const char *URL, const char *encoding, int options)

Convenience function to parse an HTML document from I/O functions and context.

xmlDoc * htmlCtxtParseDocument (htmlParserCtxt *ctxt, xmlParserInput *input)

Parse an HTML document and return the resulting document tree.

xmlDoc * htmlCtxtReadDoc (xmlParserCtxt *ctxt, const xmlChar *cur, const char *URL, const char *encoding, int options)

Parse an HTML in-memory document and build a tree.

xmlDoc * htmlCtxtReadFile (xmlParserCtxt *ctxt, const char *filename, const char *encoding, int options)

Parse an HTML file from the filesystem, the network or a user-defined resource loader.

xmlDoc * htmlCtxtReadMemory (xmlParserCtxt *ctxt, const char *buffer, int size, const char *URL, const char *encoding, int options)

Parse an HTML in-memory document and build a tree.

xmlDoc * htmlCtxtReadFd (xmlParserCtxt *ctxt, int fd, const char *URL, const char *encoding, int options)

Parse an HTML from a file descriptor and build a tree.

xmlDoc * htmlCtxtReadIO (xmlParserCtxt *ctxt, xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, void *ioctx, const char *URL, const char *encoding, int options)

Parse an HTML document from I/O functions and source and build a tree.

htmlStatus htmlAttrAllowed (const htmlElemDesc *, const xmlChar *, int)

int htmlElementAllowedHere (const htmlElemDesc *, const xmlChar *)

htmlStatus htmlElementStatusHere (const htmlElemDesc *, const htmlElemDesc *)

htmlStatus htmlNodeStatus (xmlNode *, int)

Detailed Description

HTML parser, doesn't support HTML5.

This module orginally implemented an HTML parser based on the (underspecified) HTML 4.0 spec. As of 2.14, the tokenizer conforms to HTML5. Tree construction still follows a custom, unspecified algorithm with many differences to HTML5.

The parser defaults to ISO-8859-1, the default encoding of HTTP/1.0.

Copyright: See Copyright for the status of this software.

Author: Daniel Veillard

Enumeration Type Documentation

◆ htmlParserOption

enum htmlParserOption

This is the set of HTML parser options that can be passed to htmlReadDoc, htmlCtxtSetOptions and other functions.

Enumerator
HTML_PARSE_RECOVER	No effect as of 2.14.0.
HTML_PARSE_NODEFDTD	Do not default to a doctype if none was found.
HTML_PARSE_NOERROR	Disable error and warning reports to the error handlers. Errors are still accessible with xmlCtxtGetLastError().
HTML_PARSE_NOWARNING	Disable warning reports.
HTML_PARSE_PEDANTIC	No effect.
HTML_PARSE_NOBLANKS	Remove some text nodes containing only whitespace from the result document. Which nodes are removed depends on a conservative heuristic. The reindenting feature of the serialization code relies on this option to be set when parsing. Use of this option is DISCOURAGED.
HTML_PARSE_NONET	No effect.
HTML_PARSE_NOIMPLIED	Do not add implied html, head or body elements.
HTML_PARSE_COMPACT	Store small strings directly in the node struct to save memory.
HTML_PARSE_HUGE	Relax some internal limits. See XML_PARSE_HUGE in xmlParserOption. Since 2.14.0 Use XML_PARSE_HUGE with older versions.
HTML_PARSE_IGNORE_ENC	Ignore the encoding in the HTML declaration. This option is mostly unneeded these days. The only effect is to enforce ISO-8859-1 decoding of ASCII-like data.
HTML_PARSE_BIG_LINES	Enable reporting of line numbers larger than 65535. Since 2.14.0 Use XML_PARSE_BIG_LINES with older versions.
HTML_PARSE_HTML5	Make the tokenizer emit a SAX callback for each token. This results in unbalanced invocations of startElement and endElement. For now, this is only usable to tokenize HTML5 with custom SAX callbacks. A tree builder isn't implemented yet. Since 2.14.0

Function Documentation

◆ htmlAttrAllowed()

htmlStatus htmlAttrAllowed ( const htmlElemDesc * elt,

const xmlChar * attr,

int legacy )

Deprecated: Don't use.

Parameters: elt HTML element

attr HTML attribute

legacy whether to allow deprecated attributes

Returns: HTML_VALID

◆ htmlAutoCloseTag()

int htmlAutoCloseTag ( xmlDoc * doc,

const xmlChar * name,

xmlNode * elem )

The HTML DTD allows a tag to implicitly close other tags.

The list is kept in htmlStartClose array. This function checks if the element or one of it's children would autoclose the given tag.

Deprecated: Internal function, don't use.

Parameters: doc the HTML document

name The tag name

elem the HTML element

Returns: 1 if autoclose, 0 otherwise

◆ htmlCreateFileParserCtxt()

htmlParserCtxt * htmlCreateFileParserCtxt ( const char * filename,

const char * encoding )

Create a parser context to read from a file.

Deprecated: Use htmlNewParserCtxt and htmlCtxtReadFile.

A non-NULL encoding overrides encoding declarations in the document.

Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time.

Parameters: filename the filename

encoding optional encoding

Returns: the new parser context or NULL if a memory allocation failed.

◆ htmlCreateMemoryParserCtxt()

htmlParserCtxt * htmlCreateMemoryParserCtxt ( const char * buffer,

int size )

Create a parser context for an HTML in-memory document.

The input buffer must not contain any terminating null bytes.

Deprecated: Use htmlNewParserCtxt and htmlCtxtReadMemory.

Parameters: buffer a pointer to a char array

size the size of the array

Returns: the new parser context or NULL

◆ htmlCreatePushParserCtxt()

htmlParserCtxt * htmlCreatePushParserCtxt ( htmlSAXHandler * sax,

void * user_data,

const char * chunk,

int size,

const char * filename,

xmlCharEncoding enc )

Create a parser context for using the HTML parser in push mode.

Parameters: sax a SAX handler (optional)

user_data The user data returned on SAX callbacks (optional)

chunk a pointer to an array of chars (optional)

size number of chars in the array

filename only used for error reporting (optional)

enc encoding (deprecated, pass XML_CHAR_ENCODING_NONE)

Returns: the new parser context or NULL if a memory allocation failed.

◆ htmlCtxtParseDocument()

xmlDoc * htmlCtxtParseDocument ( htmlParserCtxt * ctxt,

xmlParserInput * input )

Parse an HTML document and return the resulting document tree.

Since: 2.13.0

Parameters: ctxt an HTML parser context

input parser input

Returns: the resulting document tree or NULL

◆ htmlCtxtReadDoc()

xmlDoc * htmlCtxtReadDoc ( xmlParserCtxt * ctxt,

const xmlChar * str,

const char * URL,

const char * encoding,

int options )

Parse an HTML in-memory document and build a tree.

See htmlCtxtUseOptions for details.

Parameters: ctxt an HTML parser context

str a pointer to a zero terminated string

URL only used for error reporting (optional)

encoding the document encoding (optional)

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlCtxtReadFd()

xmlDoc * htmlCtxtReadFd ( xmlParserCtxt * ctxt,

int fd,

const char * URL,

const char * encoding,

int options )

Parse an HTML from a file descriptor and build a tree.

See htmlCtxtUseOptions for details.

NOTE that the file descriptor will not be closed when the context is freed or reset.

Parameters: ctxt an HTML parser context

fd an open file descriptor

URL only used for error reporting (optional)

encoding the document encoding (optinal)

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlCtxtReadFile()

xmlDoc * htmlCtxtReadFile ( xmlParserCtxt * ctxt,

const char * filename,

const char * encoding,

int options )

Parse an HTML file from the filesystem, the network or a user-defined resource loader.

See htmlCtxtUseOptions for details.

Parameters: ctxt an HTML parser context

filename a file or URL

encoding the document encoding (optional)

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlCtxtReadIO()

xmlDoc * htmlCtxtReadIO ( xmlParserCtxt * ctxt,

xmlInputReadCallback ioread,

xmlInputCloseCallback ioclose,

void * ioctx,

const char * URL,

const char * encoding,

int options )

Parse an HTML document from I/O functions and source and build a tree.

See htmlCtxtUseOptions for details.

Parameters: ctxt an HTML parser context

ioread an I/O read function

ioclose an I/O close function

ioctx an I/O handler

URL the base URL to use for the document

encoding the document encoding, or NULL

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlCtxtReadMemory()

xmlDoc * htmlCtxtReadMemory ( xmlParserCtxt * ctxt,

const char * buffer,

int size,

const char * URL,

const char * encoding,

int options )

Parse an HTML in-memory document and build a tree.

The input buffer must not contain any terminating null bytes.

See htmlCtxtUseOptions for details.

Parameters: ctxt an HTML parser context

buffer a pointer to a char array

size the size of the array

URL only used for error reporting (optional)

encoding the document encoding (optinal)

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlCtxtReset()

void htmlCtxtReset ( htmlParserCtxt * ctxt )

Reset a parser context.

Same as xmlCtxtReset.

Parameters: ctxt an HTML parser context

◆ htmlCtxtSetOptions()

int htmlCtxtSetOptions ( htmlParserCtxt * ctxt,

int options )

Applies the options to the parser context.

Unset options are cleared.

Since: 2.14.0

With older versions, you can use htmlCtxtUseOptions.

Parameters: ctxt an HTML parser context

options a bitmask of htmlParserOption values

Returns: 0 in case of success, the set of unknown or unimplemented options in case of error.

◆ htmlCtxtUseOptions()

int htmlCtxtUseOptions ( htmlParserCtxt * ctxt,

int options )

Applies the options to the parser context.

The following options are never cleared and can only be enabled:

Deprecated: Use htmlCtxtSetOptions.

HTML_PARSE_NODEFDTD
HTML_PARSE_NOERROR
HTML_PARSE_NOWARNING
HTML_PARSE_NOIMPLIED
HTML_PARSE_COMPACT
HTML_PARSE_HUGE
HTML_PARSE_IGNORE_ENC
HTML_PARSE_BIG_LINES

Parameters: ctxt an HTML parser context

options a combination of htmlParserOption values

Returns: 0 in case of success, the set of unknown or unimplemented options in case of error.

◆ htmlElementAllowedHere()

int htmlElementAllowedHere ( const htmlElemDesc * parent,

const xmlChar * elt )

Deprecated: Don't use.

Parameters: parent HTML parent element

elt HTML element

Returns: 1

◆ htmlElementStatusHere()

htmlStatus htmlElementStatusHere ( const htmlElemDesc * parent,

const htmlElemDesc * elt )

Deprecated: Don't use.

Parameters: parent HTML parent element

elt HTML element

Returns: HTML_VALID

◆ htmlEncodeEntities()

int htmlEncodeEntities ( unsigned char * out,

int * outlen,

const unsigned char * in,

int * inlen,

int quoteChar )

Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.

Deprecated: Only supports HTML 4.

Parameters: out a pointer to an array of bytes to store the result

outlen the length of out

in a pointer to an array of UTF-8 chars

inlen the length of in

quoteChar the quote character to escape (' or ") or zero.

Returns: 0 if success, -2 if the transcoding fails, or -1 otherwise The value of inlen after return is the number of octets consumed as the return value is positive, else unpredictable. The value of outlen after return is the number of octets consumed.

◆ htmlEntityLookup()

const htmlEntityDesc * htmlEntityLookup ( const xmlChar * name )

Lookup the given entity in EntitiesTable.

Deprecated: Only supports HTML 4.

TODO: the linear scan is really ugly, an hash table is really needed.

Parameters: name the entity name

Returns: the associated htmlEntityDesc if found, NULL otherwise.

◆ htmlEntityValueLookup()

const htmlEntityDesc * htmlEntityValueLookup ( unsigned int value )

Lookup the given entity in EntitiesTable.

Deprecated: Only supports HTML 4.

TODO: the linear scan is really ugly, an hash table is really needed.

Parameters: value the entity's unicode value

Returns: the associated htmlEntityDesc if found, NULL otherwise.

◆ htmlFreeParserCtxt()

void htmlFreeParserCtxt ( htmlParserCtxt * ctxt )

Free all the memory used by a parser context.

However the parsed document in ctxt->myDoc is not freed.

Parameters: ctxt an HTML parser context

◆ htmlHandleOmittedElem()

int htmlHandleOmittedElem ( int val )

Set and return the previous value for handling HTML omitted tags.

Deprecated: Use HTML_PARSE_NOIMPLIED

Parameters: val int 0 or 1

Returns: the last value for 0 for no handling, 1 for auto insertion.

◆ htmlInitAutoClose()

void htmlInitAutoClose ( void )

Deprecated: This is a no-op.

◆ htmlIsAutoClosed()

int htmlIsAutoClosed ( xmlDoc * doc,

xmlNode * elem )

The HTML DTD allows a tag to implicitly close other tags.

The list is kept in htmlStartClose array. This function checks if a tag is autoclosed by one of it's child

Deprecated: Internal function, don't use.

Parameters: doc the HTML document

elem the HTML element

Returns: 1 if autoclosed, 0 otherwise

◆ htmlIsScriptAttribute()

int htmlIsScriptAttribute ( const xmlChar * name )

Check if an attribute is of content type Script.

Deprecated: Only supports HTML 4.

Parameters: name an attribute name

Returns: 1 is the attribute is a script 0 otherwise

◆ htmlNewParserCtxt()

htmlParserCtxt * htmlNewParserCtxt ( void )

Allocate and initialize a new HTML parser context.

This can be used to parse HTML documents into DOM trees with functions like xmlCtxtReadFile or xmlCtxtReadMemory.

See htmlCtxtUseOptions for parser options.

See xmlCtxtSetErrorHandler for advanced error handling.

See htmlNewSAXParserCtxt for custom SAX parsers.

Returns: the htmlParserCtxt or NULL in case of allocation error

◆ htmlNewSAXParserCtxt()

htmlParserCtxt * htmlNewSAXParserCtxt ( const htmlSAXHandler * sax,

void * userData )

Allocate and initialize a new HTML SAX parser context.

If userData is NULL, the parser context will be passed as user data.

Since: 2.11.0

If you want support older versions, it's best to invoke htmlNewParserCtxt and set ctxt->sax with struct assignment.

Also see htmlNewParserCtxt.

Parameters: sax SAX handler

userData user data

Returns: the htmlParserCtxt or NULL in case of allocation error

◆ htmlNodeStatus()

htmlStatus htmlNodeStatus ( xmlNode * node,

int legacy )

Deprecated: Don't use.

Parameters: node an xmlNode in a tree

legacy whether to allow deprecated elements (YES is faster here for Element nodes)

Returns: HTML_VALID

◆ htmlParseCharRef()

int htmlParseCharRef ( htmlParserCtxt * ctxt )

Deprecated: Internal function, don't use.

Parameters: ctxt an HTML parser context

Returns: 0

◆ htmlParseChunk()

int htmlParseChunk ( htmlParserCtxt * ctxt,

const char * chunk,

int size,

int terminate )

Parse a chunk of memory in push parser mode.

Assumes that the parser context was initialized with htmlCreatePushParserCtxt.

The last chunk, which will often be empty, must be marked with the terminate flag. With the default SAX callbacks, the resulting document will be available in ctxt->myDoc. This pointer will not be freed by the library.

If the document isn't well-formed, ctxt->myDoc is set to NULL.

Since 2.14.0, xmlCtxtGetDocument can be used to retrieve the result document.

Parameters: ctxt an HTML parser context

chunk chunk of memory

size size of chunk in bytes

terminate last chunk indicator

Returns: an xmlParserErrors code (0 on success).

◆ htmlParseDoc()

xmlDoc * htmlParseDoc ( const xmlChar * cur,

const char * encoding )

Parse an HTML in-memory document and build a tree.

Deprecated: Use htmlReadDoc.

This function uses deprecated global parser options.

Parameters: cur a pointer to an array of xmlChar

encoding the encoding (optional)

Returns: the resulting document tree

◆ htmlParseDocument()

int htmlParseDocument ( htmlParserCtxt * ctxt )

Parse an HTML document and invoke the SAX handlers.

This is useful if you're only interested in custom SAX callbacks. If you want a document tree, use htmlCtxtParseDocument.

Parameters: ctxt an HTML parser context

Returns: 0, -1 in case of error.

◆ htmlParseElement()

void htmlParseElement ( htmlParserCtxt * ctxt )

This is kept for compatibility with previous code versions.

Deprecated: Internal function, don't use.

Parameters: ctxt an HTML parser context

◆ htmlParseEntityRef()

const htmlEntityDesc * htmlParseEntityRef ( htmlParserCtxt * ctxt,

const xmlChar ** str )

Deprecated: Internal function, don't use.

Parameters: ctxt an HTML parser context

str location to store the entity name

Returns: NULL.

◆ htmlParseFile()

xmlDoc * htmlParseFile ( const char * filename,

const char * encoding )

Parse an HTML file and build a tree.

Parameters: filename the filename

encoding encoding (optional)

Returns: the resulting document tree

◆ htmlReadDoc()

xmlDoc * htmlReadDoc ( const xmlChar * str,

const char * url,

const char * encoding,

int options )

Convenience function to parse an HTML document from a zero-terminated string.

See htmlCtxtReadDoc for details.

Parameters: str a pointer to a zero terminated string

url only used for error reporting (optoinal)

encoding the document encoding (optional)

options a combination of htmlParserOption values

Returns: the resulting document tree.

◆ htmlReadFd()

xmlDoc * htmlReadFd ( int fd,

const char * url,

const char * encoding,

int options )

Convenience function to parse an HTML document from a file descriptor.

NOTE that the file descriptor will not be closed when the context is freed or reset.

See htmlCtxtReadFd for details.

Parameters: fd an open file descriptor

url only used for error reporting (optional)

encoding the document encoding, or NULL

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlReadFile()

xmlDoc * htmlReadFile ( const char * filename,

const char * encoding,

int options )

Convenience function to parse an HTML file from the filesystem, the network or a global user-defined resource loader.

See htmlCtxtReadFile for details.

Parameters: filename a file or URL

encoding the document encoding (optional)

options a combination of htmlParserOption values

Returns: the resulting document tree.

◆ htmlReadIO()

xmlDoc * htmlReadIO ( xmlInputReadCallback ioread,

xmlInputCloseCallback ioclose,

void * ioctx,

const char * url,

const char * encoding,

int options )

Convenience function to parse an HTML document from I/O functions and context.

See htmlCtxtReadIO for details.

Parameters: ioread an I/O read function

ioclose an I/O close function (optional)

ioctx an I/O handler

url only used for error reporting (optional)

encoding the document encoding (optional)

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlReadMemory()

xmlDoc * htmlReadMemory ( const char * buffer,

int size,

const char * url,

const char * encoding,

int options )

Convenience function to parse an HTML document from memory.

The input buffer must not contain any terminating null bytes.

See htmlCtxtReadMemory for details.

Parameters: buffer a pointer to a char array

size the size of the array

url only used for error reporting (optional)

encoding the document encoding, or NULL

options a combination of htmlParserOption values

Returns: the resulting document tree

◆ htmlSAXParseDoc()

xmlDoc * htmlSAXParseDoc ( const xmlChar * cur,

const char * encoding,

htmlSAXHandler * sax,

void * userData )

Parse an HTML in-memory document.

If sax is not NULL, use the SAX callbacks to handle parse events. If sax is NULL, fallback to the default DOM behavior and return a tree.

Deprecated: Use htmlNewSAXParserCtxt and htmlCtxtReadDoc.

Parameters: cur a pointer to an array of xmlChar

encoding a free form C string describing the HTML document encoding, or NULL

sax the SAX handler block

userData if using SAX, this pointer will be provided on callbacks.

Returns: the resulting document tree unless SAX is NULL or the document is not well formed.

◆ htmlSAXParseFile()

xmlDoc * htmlSAXParseFile ( const char * filename,

const char * encoding,

htmlSAXHandler * sax,

void * userData )

parse an HTML file and build a tree.

Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time. It use the given SAX function block to handle the parsing callback. If sax is NULL, fallback to the default DOM tree building routines.

Deprecated: Use htmlNewSAXParserCtxt and htmlCtxtReadFile.

Parameters: filename the filename

encoding encoding (optional)

sax the SAX handler block

userData if using SAX, this pointer will be provided on callbacks.

Returns: the resulting document tree unless SAX is NULL or the document is not well formed.

◆ htmlTagLookup()

const htmlElemDesc * htmlTagLookup ( const xmlChar * tag )

Lookup the HTML tag in the ElementTable.

Deprecated: Only supports HTML 4.

Parameters: tag The tag name in lowercase

Returns: the related htmlElemDesc or NULL if not found.

◆ htmlUTF8ToHtml()

int htmlUTF8ToHtml ( unsigned char * out,

int * outlen,

const unsigned char * in,

int * inlen )

Take a block of UTF-8 chars in and try to convert it to an ASCII plus HTML entities block of chars out.

Deprecated: Internal function, don't use.

Parameters: out a pointer to an array of bytes to store the result

outlen the length of out

in a pointer to an array of UTF-8 chars

inlen the length of in

Returns: 0 if success, -2 if the transcoding fails, or -1 otherwise The value of inlen after return is the number of octets consumed as the return value is positive, else unpredictable. The value of outlen after return is the number of octets consumed.

Generated by doxygen 1.14.0